Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5152 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.4789. Min Act: -0.1700
Data Index: 1453824 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.4162. Min Act: -0.1700
Data Index: 1866028 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.3535. Min Act: -0.1700
Data Index: 2942864 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.3848. Min Act: -0.1700
Data Index: 771351 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.3535. Min Act: -0.1700
Data Index: 2844166 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.3535. Min Act: -0.1700
Data Index: 2855560 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.3535. Min Act: -0.1700
Data Index: 3474508 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.3535. Min Act: -0.1700
Data Index: 5958636 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.3221. Min Act: -0.1700
Data Index: 1267595 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.3221. Min Act: -0.1700
Data Index: 2392487 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.2907. Min Act: -0.1700
Data Index: 1625733 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.2907. Min Act: -0.1700
Data Index: 8077271 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.2907. Min Act: -0.1700
Data Index: 8044322 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.2907. Min Act: -0.1700
Data Index: 1425158 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.2907. Min Act: -0.1700
Data Index: 1610532 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.2907. Min Act: -0.1700
Data Index: 2107868 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.2593. Min Act: -0.1700
Data Index: 8325600 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.2593. Min Act: -0.1700
Data Index: 7561537 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.2593. Min Act: -0.1700
Data Index: 5854563 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4789. Min Range: -3.4789
Max Act: 3.2593. Min Act: -0.1700
Data Index: 3180433 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19